AlphaStar Masters StarCraft II

Competitions & Benchmarks The Transformer Era

Impact

At a glance

Date: January 2019
Era: The Transformer Era (2018–2021)
Category: Competitions & Benchmarks
Impact: 3 / 5
Organizations: DeepMind

What Happened

DeepMind's AlphaStar reached Grandmaster level in StarCraft II, a real-time strategy game requiring long-term planning, deception, and split-second tactics with incomplete information — far more complex than Go or chess.

Why It Mattered

Demonstrated AI could handle real-time, imperfect-information, multi-agent environments. A major step toward AI that can operate in the messy, complex real world.

Organizations

DeepMind

Frequently asked questions

When did AlphaStar Masters StarCraft II happen?+

AlphaStar Masters StarCraft II took place in January 2019.

Who was behind AlphaStar Masters StarCraft II?+

For AlphaStar Masters StarCraft II, organizations involved were DeepMind.

Why was AlphaStar Masters StarCraft II important?+

Demonstrated AI could handle real-time, imperfect-information, multi-agent environments. A major step toward AI that can operate in the messy, complex real world.

Which era of AI history does AlphaStar Masters StarCraft II belong to?+

AlphaStar Masters StarCraft II is part of the The Transformer Era era (2018–2021) — a significant development in the competitions & benchmarks category.

Related Milestones

2016.03Competition

AlphaGo Defeats Lee Sedol

DeepMind's AlphaGo defeated Lee Sedol, one of the greatest Go players ever, 4-1 in a five-game match in Seoul. Go has more possible positions than atoms in the universe — brute force was impossible. AlphaGo used deep reinforcement learning and Monte Carlo tree search. In Game 2, AlphaGo played Move 37 — a move so creative that experts called it 'beautiful' and 'not a human move.'

Demis HassabisDavid SilverDeepMindGoogle

2013.12Research

DeepMind's DQN Masters Atari Games

DeepMind demonstrated a deep reinforcement learning agent (Deep Q-Network) that learned to play Atari 2600 games directly from pixel inputs, achieving superhuman performance on many games with no task-specific engineering. Google acquired DeepMind for ~$500 million shortly after.

Volodymyr MnihDemis HassabisDeepMind

2017.10Research

AlphaGo Zero: Learning From Scratch

AlphaGo Zero achieved superhuman Go performance with ZERO human knowledge — no training data from human games, no hand-crafted features. It learned entirely through self-play, and within 40 days surpassed all previous versions, including the one that beat Lee Sedol.

David SilverDeepMind

2020.11Research

AlphaFold 2: Protein Folding Solved

DeepMind's AlphaFold 2 solved the 50-year-old protein structure prediction problem, achieving accuracy comparable to experimental methods at CASP14. It could predict how proteins fold from their amino acid sequences — a problem that had stumped biologists for half a century.

John JumperDemis HassabisDeepMind

1997.05Competition

Deep Blue Defeats Kasparov

IBM's Deep Blue defeated world chess champion Garry Kasparov in a six-game match (3.5-2.5). It was the first time a reigning world champion lost a match to a computer under standard tournament conditions. Deep Blue evaluated 200 million positions per second using brute-force search and hand-crafted evaluation.

Garry KasparovIBM

Get the latest AI milestones as they happen

Join the newsletter. No spam, just signal.